import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

df=pd.read_csv("states.csv")

df.describe(exclude='object')

df.describe(include='object')

import pandas as pd

# Check unique country names in the DataFrame
unique_countries = df['state_name'].unique()
print(unique_countries)

['United States of America' 'Canada' 'Bahamas' 'Cuba' 'Haiti'
 'Dominican Republic' 'Jamaica' 'Trinidad and Tobago' 'Barbados'
 'Dominica' 'Grenada' 'St. Lucia' 'St. Vincent and the Grenadines'
 'Antigua & Barbuda' 'St. Kitts and Nevis' 'Mexico' 'Belize' 'Guatemala'
 'Honduras' 'El Salvador' 'Nicaragua' 'Costa Rica' 'Panama' 'Colombia'
 'Venezuela' 'Guyana' 'Suriname' 'Ecuador' 'Peru' 'Brazil' 'Bolivia'
 'Paraguay' 'Chile' 'Argentina' 'Uruguay' 'United Kingdom' 'Ireland'
 'Netherlands' 'Belgium' 'Luxembourg' 'France' 'Monaco' 'Liechtenstein'
 'Switzerland' 'Spain' 'Andorra' 'Portugal' 'German Federal Republic'
 'German Democratic Republic' 'Poland' 'Austria' 'Hungary'
 'Czechoslovakia' 'Czech Republic' 'Slovakia' 'Italy' 'San Marino' 'Malta'
 'Albania' 'Montenegro' nan 'Macedonia' 'Croatia' 'Yugoslavia'
 'Bosnia and Herzegovina' 'Slovenia' 'Greece' 'Cyprus' 'Bulgaria'
 'Moldova' 'Romania' 'Russia' 'Estonia' 'Latvia' 'Lithuania' 'Ukraine'
 'Belarus' 'Armenia' 'Georgia' 'Azerbaijan' 'Finland' 'Sweden' 'Norway'
 'Denmark' 'Iceland' 'Cape Verde' 'Sao Tome and Principe' 'Guinea-Bissau'
 'Equatorial Guinea' 'Gambia' 'Mali' 'Senegal' 'Benin' 'Mauritania'
 'Niger' 'Ivory Coast' 'Guinea' 'Burkina Faso' 'Liberia' 'Sierra Leone'
 'Ghana' 'Togo' 'Cameroon' 'Nigeria' 'Gabon' 'Central African Republic'
 'Chad' 'Congo' 'Democratic Republic of the Congo' 'Uganda' 'Kenya'
 'Tanzania' 'Burundi' 'Rwanda' 'Somalia' 'Djibouti' 'Ethiopia' 'Eritrea'
 'Angola' 'Mozambique' 'Zambia' 'Zimbabwe' 'Malawi' 'South Africa'
 'Namibia' 'Lesotho' 'Botswana' 'Swaziland' 'Madagascar' 'Comoros'
 'Mauritius' 'Seychelles' 'Morocco' 'Algeria' 'Tunisia' 'Libya' 'Sudan'
 'South Sudan' 'Iran' 'Turkey' 'Iraq' 'Egypt' 'Syria' 'Lebanon' 'Jordan'
 'Israel' 'Saudi Arabia' 'Yemen Arab Republic' "Yemen People's Republic"
 'Kuwait' 'Bahrain' 'Qatar' 'United Arab Emirates' 'Oman' 'Afghanistan'
 'Turkmenistan' 'Tajikistan' 'Kyrgyzstan' 'Uzbekistan' 'Kazakhstan'
 'China' 'Mongolia' 'Taiwan' 'North Korea' 'South Korea' 'Japan' 'India'
 'Bhutan' 'Pakistan' 'Bangladesh' 'Myanmar' 'Sri Lanka' 'Maldives' 'Nepal'
 'Thailand' 'Cambodia' 'Laos' 'Vietnam' 'Malaysia' 'Singapore' 'Brunei'
 'Philippines' 'Indonesia' 'East Timor' 'Australia' 'Papua New Guinea'
 'New Zealand' 'Vanuatu' 'Solomon Islands' 'Kiribati' 'Tuvalu' 'Fiji'
 'Tonga' 'Nauru' 'Marshall Islands' 'Palau'
 'Federated States of Micronesia' 'Samoa']

unique_countries_count = df['state_name'].nunique()
print(unique_countries_count)

197

df.head(20)

df.tail(20)

print(df.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9705 entries, 0 to 9704
Data columns (total 15 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   year                  9697 non-null   float64
 1   assembly_session      9697 non-null   float64
 2   state_code            9705 non-null   int64  
 3   state_name            9697 non-null   object 
 4   all_votes             9697 non-null   float64
 5   yes_votes             9697 non-null   float64
 6   no_votes              9697 non-null   float64
 7   abstain               9697 non-null   float64
 8   idealpoint_estimate   9697 non-null   float64
 9   affinityscore_usa     9696 non-null   float64
 10  affinityscore_russia  9692 non-null   float64
 11  affinityscore_china   7608 non-null   float64
 12  affinityscore_india   9696 non-null   float64
 13  affinityscore_brazil  9696 non-null   float64
 14  affinityscore_israel  9585 non-null   float64
dtypes: float64(13), int64(1), object(1)
memory usage: 1.1+ MB
None

df.isnull().sum()

year                       8
assembly_session           8
state_code                 0
state_name                 8
all_votes                  8
yes_votes                  8
no_votes                   8
abstain                    8
idealpoint_estimate        8
affinityscore_usa          9
affinityscore_russia      13
affinityscore_china     2097
affinityscore_india        9
affinityscore_brazil       9
affinityscore_israel     120
dtype: int64

# Drop rows with null values in the 'state_name' column
df = df.dropna(subset=['state_name'])

df.isnull().sum()

year                       0
assembly_session           0
state_code                 0
state_name                 0
all_votes                  0
yes_votes                  0
no_votes                   0
abstain                    0
idealpoint_estimate        0
affinityscore_usa          1
affinityscore_russia       5
affinityscore_china     2089
affinityscore_india        1
affinityscore_brazil       1
affinityscore_israel     112
dtype: int64

sns.heatmap(df.isnull(),yticklabels=False,cmap='flare')

<Axes: >

df.shape

(9697, 15)

# Calculate the mean of each column
mean_affinityscore_usa = df['affinityscore_usa'].mean()
mean_affinityscore_russia = df['affinityscore_russia'].mean()
mean_affinityscore_india = df['affinityscore_india'].mean()
mean_affinityscore_brazil = df['affinityscore_brazil'].mean()
mean_affinityscore_israel = df['affinityscore_israel'].mean()
mean_affinityscore_china = df['affinityscore_china'].mean()

# Replace null values with mean of each column using .loc accessor
df.loc[df['affinityscore_usa'].isnull(), 'affinityscore_usa'] = mean_affinityscore_usa
df.loc[df['affinityscore_russia'].isnull(), 'affinityscore_russia'] = mean_affinityscore_russia
df.loc[df['affinityscore_india'].isnull(), 'affinityscore_india'] = mean_affinityscore_india
df.loc[df['affinityscore_brazil'].isnull(), 'affinityscore_brazil'] = mean_affinityscore_brazil
df.loc[df['affinityscore_israel'].isnull(), 'affinityscore_israel'] = mean_affinityscore_israel
df.loc[df['affinityscore_china'].isnull(), 'affinityscore_china'] = mean_affinityscore_china

import matplotlib.pyplot as plt

# Calculate the mean affinity score for each country
mean_affinity_usa = df['affinityscore_usa'].mean()
mean_affinity_russia = df['affinityscore_russia'].mean()
mean_affinity_china = df['affinityscore_china'].mean()
mean_affinity_india = df['affinityscore_india'].mean()
mean_affinity_brazil = df['affinityscore_brazil'].mean()
mean_affinity_israel = df['affinityscore_israel'].mean()

# Create lists of means and corresponding countries
countries = ['USA', 'Russia', 'China', 'India', 'Brazil', 'Israel']
means = [mean_affinity_usa, mean_affinity_russia, mean_affinity_china, mean_affinity_india, mean_affinity_brazil, mean_affinity_israel]

# Plotting the mean affinity scores
plt.figure(figsize=(10, 6))
plt.bar(countries, means, color=['blue', 'violet', 'red', 'orange', 'purple', 'pink'])
plt.xlabel('Country')
plt.ylabel('Mean Affinity Score')
plt.title('Mean Affinity Score Comparison of Countries')
plt.grid(axis='y')
plt.show()

df.isnull().sum()

year                    0
assembly_session        0
state_code              0
state_name              0
all_votes               0
yes_votes               0
no_votes                0
abstain                 0
idealpoint_estimate     0
affinityscore_usa       0
affinityscore_russia    0
affinityscore_china     0
affinityscore_india     0
affinityscore_brazil    0
affinityscore_israel    0
dtype: int64

df.describe()

df.nunique()

year                      69
assembly_session          69
state_code               198
state_name               197
all_votes                158
yes_votes                157
no_votes                  70
abstain                   71
idealpoint_estimate     8377
affinityscore_usa       2257
affinityscore_russia    2411
affinityscore_china     1687
affinityscore_india     2276
affinityscore_brazil    2120
affinityscore_israel    2023
dtype: int64

import matplotlib.pyplot as plt
# Histograms for each numerical feature
df.hist(bins=20, figsize=(15, 10))
plt.show()

countries = ['USA', 'Russia', 'China', 'India', 'Brazil', 'Israel']
means = [mean_affinity_usa, mean_affinity_russia, mean_affinity_china, mean_affinity_india, mean_affinity_brazil, mean_affinity_israel]

# Plotting the mean affinity scores as a pie chart
plt.figure(figsize=(8, 8))
plt.pie(means, labels=countries, autopct='%1.1f%%', startangle=140)
plt.title('Mean Affinity Score Comparison of Countries')
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# Assuming you have loaded your dataset into a DataFrame named df
# Let's group the DataFrame by 'state_name' and 'assembly_session' and calculate the sum of votes
grouped_df = df.groupby(['state_name', 'assembly_session']).sum().reset_index()

# Stacked Bar Plot for Yes, No, and Abstain votes
plt.figure(figsize=(20, 15))
for country, data in grouped_df.groupby('state_name'):
    plt.bar(data['assembly_session'], data['yes_votes'], label=f'{country} Yes', alpha=0.7)
    plt.bar(data['assembly_session'], data['no_votes'], bottom=data['yes_votes'], label=f'{country} No', alpha=0.7)
    plt.bar(data['assembly_session'], data['abstain'], bottom=data['yes_votes']+data['no_votes'], label=f'{country} Abstain', alpha=0.7)

plt.xlabel('Assembly Session')
plt.ylabel('Votes')
plt.title('Votes by Country and Assembly Session')
plt.legend()
plt.show()

/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/IPython/core/pylabtools.py:170: UserWarning: Creating legend with loc="best" can be slow with large amounts of data.
  fig.canvas.print_figure(bytes_io, **kw)

import matplotlib.pyplot as plt

# Assuming you have already defined grouped_df correctly
plt.figure(figsize=(15, 10))
for country, data in grouped_df.groupby('state_name'):
    plt.fill_between(data['assembly_session'], data['yes_votes'], label=f'{country} Yes', alpha=0.7)
    plt.fill_between(data['assembly_session'], data['no_votes'], label=f'{country} No', alpha=0.7)
    plt.fill_between(data['assembly_session'], data['abstain'], label=f'{country} Abstain', alpha=0.7)

plt.xlabel('Assembly Session')
plt.ylabel('Votes')
plt.title('Votes by Country and Assembly Session')
plt.legend()
plt.show()

# Create a pivot table for heatmap
heatmap_df = grouped_df.pivot(index='assembly_session', columns='state_name', values=['yes_votes', 'no_votes', 'abstain'])

# Heatmap
plt.figure(figsize=(12, 8))
sns.heatmap(heatmap_df, cmap='viridis', linewidths=0.5)
plt.title('Votes by Country and Assembly Session')
plt.xlabel('Country')
plt.ylabel('Assembly Session')
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# Assuming your DataFrame is named df

# Filter data for the desired countries
desired_countries = ['Brazil', 'China', 'United States of America', 'Israel', 'Russia', 'India']
filtered_df = df[df['state_name'].isin(desired_countries)]

# Group by assembly session and calculate sum of yes, no, and abstain votes
grouped_df = filtered_df.groupby(['assembly_session', 'state_name']).sum().reset_index()

# Plotting
fig, axes = plt.subplots(nrows=3, ncols=1, figsize=(12, 18))  # Adjusted figsize
fig.patch.set_facecolor('#f5f5f5')  # Set background color for the figure
fig.patch.set_linewidth(1)  # Set border width for the figure
fig.patch.set_edgecolor('black')  # Set border color for the figure

# Set background color for the plot area
for ax in axes:
    ax.set_facecolor('#e5e5e5')  # Set background color for the plot area
    ax.spines['top'].set_visible(True)  # Show top spine/border
    ax.spines['right'].set_visible(True)  # Show right spine/border
    ax.spines['bottom'].set_linewidth(1)  # Set border width for the bottom spine
    ax.spines['left'].set_linewidth(1)  # Set border width for the left spine
    ax.spines['top'].set_linewidth(1)  # Set border width for the top spine
    ax.spines['right'].set_linewidth(1)  # Set border width for the right spine

# Plot for Yes votes
axes[0].set_title('Yes Votes by Country for Each Assembly Session', fontsize=16, fontweight='bold', color='blue')
for country, data in grouped_df.groupby('state_name'):
    axes[0].plot(data['assembly_session'], data['yes_votes'], label=country, linewidth=2)
axes[0].set_xlabel('Assembly Session', fontsize=14)
axes[0].set_ylabel('Yes Votes', fontsize=14)
axes[0].legend(fontsize=12)
axes[0].grid(True, linestyle='--', alpha=0.5)  # Add grid lines

# Plot for No votes
axes[1].set_title('No Votes by Country for Each Assembly Session', fontsize=16, fontweight='bold', color='red')
for country, data in grouped_df.groupby('state_name'):
    axes[1].plot(data['assembly_session'], data['no_votes'], label=country, linewidth=2)
axes[1].set_xlabel('Assembly Session', fontsize=14)
axes[1].set_ylabel('No Votes', fontsize=14)
axes[1].legend(fontsize=12)
axes[1].grid(True, linestyle='--', alpha=0.5)  # Add grid lines

# Plot for Abstain votes
axes[2].set_title('Abstain Votes by Country for Each Assembly Session', fontsize=16, fontweight='bold', color='green')
for country, data in grouped_df.groupby('state_name'):
    axes[2].plot(data['assembly_session'], data['abstain'], label=country, linewidth=2)
axes[2].set_xlabel('Assembly Session', fontsize=14)
axes[2].set_ylabel('Abstain Votes', fontsize=14)
axes[2].legend(fontsize=12)
axes[2].grid(True, linestyle='--', alpha=0.5)  # Add grid lines

plt.tight_layout()
plt.show()

# Calculate the mean affinity score for each country
mean_affinity_usa = df['affinityscore_usa'].mean()
mean_affinity_russia = df['affinityscore_russia'].mean()
mean_affinity_china = df['affinityscore_china'].mean()
mean_affinity_india = df['affinityscore_india'].mean()
mean_affinity_brazil = df['affinityscore_brazil'].mean()
mean_affinity_israel = df['affinityscore_israel'].mean()

# Create lists of means and corresponding countries
countries = ['USA', 'Russia', 'China', 'India', 'Brazil', 'Israel']
means = [mean_affinity_usa, mean_affinity_russia, mean_affinity_china, mean_affinity_india, mean_affinity_brazil, mean_affinity_israel]

# Create the Highcharts HTML code
highcharts_html = """
<!DOCTYPE html>
<html>
<head>
  <title>Mean Affinity Score Comparison of Countries</title>
  <script src="https://code.highcharts.com/highcharts.js"></script>
</head>
<body>

<div id="container" style="width: 600px; height: 400px; margin: 0 auto"></div>

<script>
Highcharts.chart('container', {{
  chart: {{
    type: 'bar'
  }},
  title: {{
    text: 'Mean Affinity Score Comparison of Countries'
  }},
  xAxis: {{
    categories: {categories}
  }},
  yAxis: {{
    title: {{
      text: 'Mean Affinity Score'
    }}
  }},
  series: [{{
    name: 'Mean Affinity Score',
    data: {means}
  }}]
}});
</script>

</body>
</html>
""".format(categories=countries, means=means)


# Save the HTML output to a file or display it
print(highcharts_html)

<!DOCTYPE html>
<html>
<head>
  <title>Mean Affinity Score Comparison of Countries</title>
  <script src="https://code.highcharts.com/highcharts.js"></script>
</head>
<body>

<div id="container" style="width: 600px; height: 400px; margin: 0 auto"></div>

<script>
Highcharts.chart('container', {
  chart: {
    type: 'bar'
  },
  title: {
    text: 'Mean Affinity Score Comparison of Countries'
  },
  xAxis: {
    categories: ['USA', 'Russia', 'China', 'India', 'Brazil', 'Israel']
  },
  yAxis: {
    title: {
      text: 'Mean Affinity Score'
    }
  },
  series: [{
    name: 'Mean Affinity Score',
    data: [0.29358908828382835, 0.620303931077177, 0.7525578338590958, 0.6873531043729373, 0.7338206373762376, 0.3505397496087637]
  }]
});
</script>

</body>
</html>

html_content = """
<!DOCTYPE html>
<html>
<head>
  <title>Mean Affinity Score Comparison of Countries</title>
  <script src="https://code.highcharts.com/highcharts.js"></script>
</head>
<body>

<div id="container" style="width: 600px; height: 400px; margin: 0 auto"></div>

<script>
Highcharts.chart('container', {
  chart: {
    type: 'bar'
  },
  title: {
    text: 'Mean Affinity Score Comparison of Countries'
  },
  xAxis: {
    categories: ['USA', 'Russia', 'China', 'India', 'Brazil', 'Israel']
  },
  yAxis: {
    title: {
      text: 'Mean Affinity Score'
    }
  },
  series: [{
    name: 'Mean Affinity Score',
    data: [0.29358908828382835, 0.620303931077177, 0.6659521023958656, 0.6873531043729373, 0.7338206373762376, 0.3505397496087637]
  }]
});
</script>

</body>
</html>
"""

# Write the HTML content to a file
with open('affinity_score_comparison.html', 'w') as file:
    file.write(html_content)

print("HTML file saved successfully!")

HTML file saved successfully!

import pandas as pd
import matplotlib.pyplot as plt

# Assuming 'df' is your DataFrame with columns 'yes_votes', 'no_votes', and 'abstain'

# Step 1: Calculate the sum of each column
sum_yes_votes = df['yes_votes'].sum()
sum_no_votes = df['no_votes'].sum()
sum_abstain = df['abstain'].sum()

# Step 2: Add up the sums of the three columns to get the total
total_votes = sum_yes_votes + sum_no_votes + sum_abstain

# Step 3: Calculate the percentage of each sum
yes_percentage = (sum_yes_votes / total_votes) * 100
no_percentage = (sum_no_votes / total_votes) * 100
abstain_percentage = (sum_abstain / total_votes) * 100

# Step 4: Create a pie chart
labels = ['Yes', 'No', 'Abstain']
sizes = [yes_percentage, no_percentage, abstain_percentage]
colors = ['green', 'red', 'yellow']
explode = (0.1, 0, 0)  # explode 1st slice (optional)

plt.pie(sizes, explode=explode, labels=labels, colors=colors, autopct='%1.1f%%', shadow=True, startangle=140)
plt.axis('equal')  # Equal aspect ratio ensures that pie is drawn as a circle.
plt.title('Total Votes Distribution')
plt.show()

# Time Series Analysis
plt.figure(figsize=(10, 6))
sns.lineplot(x='year', y='all_votes', data=df)
plt.title('Trend of All Votes over Years')
plt.xlabel('Year')
plt.ylabel('All Votes')
plt.show()

# Correlation Analysis
# correlation_matrix = df.corr()
# plt.figure(figsize=(10, 8))
# sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm')
# plt.title('Correlation Matrix')
# plt.show()
numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns
numeric_data = df[numeric_columns]

# Visualize correlation matrix
correlation_matrix = numeric_data.corr()
plt.figure(figsize=(10, 8))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix')
plt.show()

# Distribution Analysis
plt.figure(figsize=(12, 6))
sns.histplot(df['idealpoint_estimate'], kde=True, bins=30)
plt.title('Distribution of Ideal Point Estimate')
plt.xlabel('Ideal Point Estimate')
plt.ylabel('Frequency')
plt.show()

# import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Load the data (replace 'data.csv' with your actual file path)
# data = pd.read_csv('data.csv')

# Prepare data
X = df[['affinityscore_usa', 'affinityscore_russia',
          'affinityscore_china', 'affinityscore_india', 
          'affinityscore_brazil', 'affinityscore_israel']]
y = df['yes_votes'].apply(lambda x: 'high' if x > df['yes_votes'].mean() else 'low')  # Target variable

# Split data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initialize and train the model
clf = RandomForestClassifier()
clf.fit(X_train, y_train)

# Predictions
y_pred = clf.predict(X_test)


# Model Evaluation
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
print("Classification Report:")
print(classification_report(y_test, y_pred))
print(confusion_matrix(y_test, y_pred))

Accuracy: 0.9010309278350516
Classification Report:
              precision    recall  f1-score   support

        high       0.86      0.92      0.89       840
         low       0.94      0.89      0.91      1100

    accuracy                           0.90      1940
   macro avg       0.90      0.90      0.90      1940
weighted avg       0.90      0.90      0.90      1940

[[773  67]
 [125 975]]

import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix

# Generate classification report
report = classification_report(y_test, y_pred, output_dict=True)

# Convert the classification report to a DataFrame
report_df = pd.DataFrame(report).transpose()

# Plot the heatmap
plt.figure(figsize=(10, 6))
sns.heatmap(report_df.iloc[:-1, :-1], annot=True, cmap="YlGnBu", fmt=".2f")
plt.title('Classification Report Heatmap')
plt.xlabel('Metrics')
plt.ylabel('Class')
plt.show()

import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt



# Prepare data
X = df[['affinityscore_usa', 'affinityscore_russia',
          'affinityscore_china', 'affinityscore_india', 
          'affinityscore_brazil', 'affinityscore_israel']]

# Initialize and fit K-means model
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(X)

# Add cluster labels to the DataFrame
df['cluster'] = kmeans.labels_

# Visualize clusters
plt.figure(figsize=(10, 6))
sns.scatterplot(x='yes_votes', y='no_votes', hue='cluster', data=df, palette='Set1', legend='full')
plt.title('Clustering of States based on Voting Behavior')
plt.xlabel('Yes Votes')
plt.ylabel('No Votes')
plt.show()

/var/folders/4y/p5wbs2392ng1qdh47g8kk6x00000gn/T/ipykernel_38761/2939899213.py:17: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['cluster'] = kmeans.labels_

from sklearn.metrics import silhouette_score

# Calculate silhouette score
silhouette_avg = silhouette_score(X, kmeans.labels_)
print("Silhouette Score:", silhouette_avg)

Silhouette Score: 0.40464240364072335

import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
import seaborn as sns

# Prepare data
X = df[['affinityscore_usa', 'affinityscore_russia',
          'affinityscore_china', 'affinityscore_india', 
          'affinityscore_brazil', 'affinityscore_israel']]

# Initialize and fit K-means model
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(X)

# Add cluster labels to the DataFrame
df['cluster'] = kmeans.labels_

# Visualize clusters
plt.figure(figsize=(10, 6))
sns.scatterplot(x='affinityscore_india', y='affinityscore_china', hue='cluster', data=df, palette='Set1', legend='full')
plt.title('Clustering of States based on Affinity Scores')
plt.xlabel('Affinity Score - Inida')
plt.ylabel('Affinity Score - China')
plt.show()

/var/folders/4y/p5wbs2392ng1qdh47g8kk6x00000gn/T/ipykernel_38761/2696341349.py:16: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['cluster'] = kmeans.labels_

from sklearn.metrics import silhouette_score

# Calculate silhouette score
silhouette_avg = silhouette_score(X, kmeans.labels_)
print("Silhouette Score:", silhouette_avg)

Silhouette Score: 0.40464240364072335

# Group the data by state and calculate the sum of votes for each category
state_votes = df.groupby('state_name')[['all_votes', 'yes_votes', 'no_votes', 'abstain']].sum()

# Plotting bar charts for each voting category
state_votes.plot(kind='bar', stacked=True, figsize=(50, 20))
plt.title('Voting Patterns Across Different States')
plt.xlabel('State')
plt.ylabel('Number of Votes')
plt.xticks(rotation=45)  # Rotate state names for better readability
plt.legend(title='Vote Category')
plt.tight_layout()  # Corrected attribute name
plt.show()

# Calculate the sum of votes for each category
vote_distribution = df[['all_votes', 'yes_votes', 'no_votes', 'abstain']].sum()

# Plotting bar chart for vote distribution
plt.figure(figsize=(10, 6))
vote_distribution.plot(kind='bar', color=['blue', 'green', 'red', 'orange'])
plt.title('Vote Distribution')
plt.xlabel('Vote Type')
plt.ylabel('Number of Votes')
plt.xticks(rotation=45)  # Rotate x-axis labels for better readability
plt.show()

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score



# Data preprocessing
# For simplicity, let's assume 'state_name' is the target variable and other columns are features
X = df.drop(columns=['state_name'])  # Features
y = df['state_name']  # Target

# Encode categorical variables
le = LabelEncoder()
y = le.fit_transform(y)

# Splitting the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Model training
model = RandomForestClassifier()
model.fit(X_train, y_train)

# Model evaluation
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

Accuracy: 0.5252577319587629

import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

# Data preprocessing
# For simplicity, let's assume 'state_name' is dropped as we are clustering based on voting patterns
X = df.drop(columns=['state_name'])

# Model training
kmeans = KMeans(n_clusters=3)  # Specify the number of clusters
kmeans.fit(X)

# Visualizing clusters
plt.scatter(X['no_votes'], X['yes_votes'], c=kmeans.labels_, cmap='viridis')
plt.xlabel('No Votes')
plt.ylabel('Yes Votes')
plt.title('Clustering of States based on Voting Patterns')
plt.show()

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# Assuming df is your DataFrame containing the data

# Data preprocessing
X = df['affinityscore_china']  # Features
y = df['affinityscore_india']  # Target

# Reshape X and y to be two-dimensional arrays
X = X.values.reshape(-1, 1)  # Reshape X to a column vector
y = y.values.reshape(-1, 1)  # Reshape y to a column vector

# Splitting the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Model training
model = LinearRegression()
model.fit(X_train, y_train)

# Model evaluation
y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)

Mean Squared Error: 0.015783713134011237

import matplotlib.pyplot as plt

# Plotting the relationship between the independent variable (X) and the dependent variable (y)
plt.figure(figsize=(8, 6))
plt.scatter(X, y, color='blue', alpha=0.5)
plt.title('Scatter Plot of affinityscore_china vs. affinityscore_india')
plt.xlabel('affinityscore_china')
plt.ylabel('affinityscore_india')
plt.grid(True)
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.arima.model import ARIMA

# Assuming 'year' is the time variable and 'all_votes' is the target variable
ts_data = df[['year', 'all_votes']]
ts_data.set_index('year', inplace=True)

# Model training
model = ARIMA(ts_data, order=(5,1,0))
fit_model = model.fit()

# Forecasting
forecast_index = pd.date_range(start='2025', end='2050', freq='Y')  # Generating date range for forecasting
forecast = fit_model.forecast(steps=len(forecast_index))  # Forecasting until 2050

# Plotting forecast
plt.plot(ts_data, label='Actual')
plt.plot(forecast_index, forecast, label='Forecast')
plt.title('Forecasting Future Voting Patterns')
plt.xlabel('Year')
plt.ylabel('Number of Votes')
plt.legend()
plt.show()

/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/var/folders/4y/p5wbs2392ng1qdh47g8kk6x00000gn/T/ipykernel_38761/1475418556.py:14: FutureWarning: 'Y' is deprecated and will be removed in a future version, please use 'YE' instead.
  forecast_index = pd.date_range(start='2025', end='2050', freq='Y')  # Generating date range for forecasting
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:836: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.
  return get_prediction_index(
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:836: FutureWarning: No supported index is available. In the next version, calling this method in a model without a supported index will result in an exception.
  return get_prediction_index(

# Calculate residuals
residuals = y_test - y_pred

# Plot residuals
plt.figure(figsize=(8, 6))
plt.scatter(y_pred, residuals, color='blue', alpha=0.5)
plt.axhline(y=0, color='red', linestyle='--')
plt.title('Residuals Plot')
plt.xlabel('Predicted Values')
plt.ylabel('Residuals')
plt.show()

from sklearn.metrics import mean_squared_error
import numpy as np

# Splitting the dataset into training and testing sets
train_size = int(len(target_data) * 0.8)  # Using 80% of the data for training
train_data, test_data = target_data.iloc[:train_size], target_data.iloc[train_size:]

# Model training
model = ARIMA(train_data, order=(5, 1, 0))
fit_model = model.fit()

# Forecasting
forecast = fit_model.forecast(steps=len(test_data))  # Forecasting on the testing data

# Calculate Mean Squared Error (MSE)
mse = mean_squared_error(test_data, forecast)

# Calculate Root Mean Squared Error (RMSE)
rmse = np.sqrt(mse)

print("Mean Squared Error (MSE):", mse)
print("Root Mean Squared Error (RMSE):", rmse)

/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)

Mean Squared Error (MSE): 1145.1768315695354
Root Mean Squared Error (RMSE): 33.84046145621444

/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:836: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.
  return get_prediction_index(
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:836: FutureWarning: No supported index is available. In the next version, calling this method in a model without a supported index will result in an exception.
  return get_prediction_index(

from sklearn.metrics import mean_squared_error
import numpy as np

# Splitting the dataset into training and testing sets
train_size = int(len(target_data) * 0.8)  # Using 80% of the data for training
train_data, test_data = target_data.iloc[:train_size], target_data.iloc[train_size:]

# Model training
model = ARIMA(train_data, order=(5, 1, 0))
fit_model = model.fit()

# Forecasting
forecast = fit_model.forecast(steps=len(test_data))  # Forecasting on the testing data

# Calculate Mean Squared Error (MSE)
mse = mean_squared_error(test_data, forecast)

# Calculate Root Mean Squared Error (RMSE)
rmse = np.sqrt(mse)

print("Mean Squared Error (MSE):", mse)
print("Root Mean Squared Error (RMSE):", rmse)

# Print the forecast
print("Forecast:")
print(forecast)

/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:473: ValueWarning: An unsupported index was provided and will be ignored when e.g. forecasting.
  self._init_dates(dates, freq)

Mean Squared Error (MSE): 1145.1768315695354
Root Mean Squared Error (RMSE): 33.84046145621444
Forecast:
7757    64.542714
7758    64.554631
7759    65.089764
7760    64.674080
7761    64.790490
          ...    
9692    64.779412
9693    64.779412
9694    64.779412
9695    64.779412
9696    64.779412
Name: predicted_mean, Length: 1940, dtype: float64

/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:836: ValueWarning: No supported index is available. Prediction results will be given with an integer index beginning at `start`.
  return get_prediction_index(
/Users/shrutimall/.local/pipx/.cache/5c9468f9a0a782a/lib/python3.12/site-packages/statsmodels/tsa/base/tsa_model.py:836: FutureWarning: No supported index is available. In the next version, calling this method in a model without a supported index will result in an exception.
  return get_prediction_index(

	year	assembly_session	state_code	all_votes	yes_votes	no_votes	abstain	idealpoint_estimate	affinityscore_usa	affinityscore_russia	affinityscore_china	affinityscore_india	affinityscore_brazil	affinityscore_israel	cluster
count	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000
mean	1987.037125	42.037125	446.914613	75.246674	59.793235	5.647932	9.805507	-0.000279	0.293589	0.620304	0.752558	0.687353	0.733821	0.350540	1.061978
std	18.478671	18.478671	258.472010	33.043167	32.657278	8.268681	9.713783	0.989763	0.203660	0.202982	0.160692	0.195748	0.186575	0.189557	0.925201
min	1946.000000	1.000000	2.000000	1.000000	0.000000	0.000000	0.000000	-2.562400	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	1973.000000	28.000000	220.000000	58.000000	38.000000	0.000000	4.000000	-0.661100	0.140800	0.512200	0.723100	0.526300	0.615400	0.193500	0.000000
50%	1989.000000	44.000000	437.000000	68.000000	57.000000	2.000000	7.000000	-0.175500	0.235300	0.652200	0.761200	0.754100	0.800000	0.325900	1.000000
75%	2003.000000	58.000000	660.000000	86.000000	71.000000	9.000000	13.000000	0.808900	0.388100	0.737700	0.869600	0.835800	0.880000	0.466700	2.000000
max	2015.000000	70.000000	990.000000	158.000000	156.000000	98.000000	73.000000	3.004200	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	2.000000

	year	assembly_session	state_code	state_name	all_votes	yes_votes	no_votes	abstain	idealpoint_estimate	affinityscore_usa	affinityscore_russia	affinityscore_china	affinityscore_india	affinityscore_brazil	affinityscore_israel
0	1946.0	1.0	2	United States of America	42.0	25.0	15.0	2.0	1.7377	1.0	0.2143	0.752558	0.4762	0.6429	0.35054
1	1947.0	2.0	2	United States of America	38.0	27.0	10.0	1.0	1.8417	1.0	0.2632	0.752558	0.2973	0.8421	0.35054
2	1948.0	3.0	2	United States of America	103.0	46.0	54.0	3.0	1.9909	1.0	0.1275	0.752558	0.3700	0.7767	0.16670
3	1949.0	4.0	2	United States of America	63.0	17.0	33.0	13.0	1.9395	1.0	0.1111	0.752558	0.3651	0.5397	0.51610
4	1950.0	5.0	2	United States of America	53.0	26.0	25.0	2.0	1.8651	1.0	0.1731	0.752558	0.5094	0.8113	0.60420
5	1951.0	6.0	2	United States of America	25.0	10.0	11.0	4.0	1.8919	1.0	0.1200	0.752558	0.3600	0.6400	0.65220
6	1952.0	7.0	2	United States of America	49.0	25.0	19.0	5.0	1.9617	1.0	0.1429	0.752558	0.3061	0.6531	0.63270
7	1953.0	8.0	2	United States of America	25.0	12.0	6.0	7.0	1.7707	1.0	0.2000	0.752558	0.3333	0.6400	0.52000
8	1954.0	9.0	2	United States of America	30.0	18.0	3.0	9.0	1.5565	1.0	0.2000	0.752558	0.3000	0.6333	0.43330
9	1955.0	10.0	2	United States of America	27.0	13.0	8.0	6.0	1.8166	1.0	0.1481	0.752558	0.1111	0.7778	0.48150
10	1956.0	11.0	2	United States of America	60.0	44.0	11.0	5.0	1.3449	1.0	0.2167	0.752558	0.3667	0.9167	0.58330
11	1957.0	12.0	2	United States of America	34.0	22.0	7.0	5.0	1.3156	1.0	0.2353	0.752558	0.4118	0.8235	0.61760
12	1958.0	13.0	2	United States of America	33.0	25.0	4.0	4.0	1.3081	1.0	0.3030	0.752558	0.4848	0.8485	0.65630
13	1959.0	14.0	2	United States of America	54.0	23.0	17.0	14.0	1.6179	1.0	0.1296	0.752558	0.3396	0.7593	0.70590
14	1960.0	15.0	2	United States of America	103.0	53.0	36.0	14.0	1.5740	1.0	0.2330	0.752558	0.2913	0.7184	0.67350
15	1961.0	16.0	2	United States of America	73.0	36.0	26.0	11.0	1.7276	1.0	0.1096	0.752558	0.2466	0.6986	0.61640
16	1962.0	17.0	2	United States of America	46.0	28.0	13.0	5.0	1.9215	1.0	0.1739	0.752558	0.4889	0.6087	0.52380
17	1963.0	18.0	2	United States of America	31.0	15.0	6.0	10.0	1.9040	1.0	0.1290	0.752558	0.3871	0.5484	0.50000
18	1965.0	20.0	2	United States of America	40.0	14.0	15.0	11.0	2.0057	1.0	0.2250	0.752558	0.3500	0.5750	0.53850
19	1966.0	21.0	2	United States of America	50.0	19.0	20.0	11.0	2.0598	1.0	0.1600	0.752558	0.2200	0.6000	0.68750

	year	assembly_session	state_code	state_name	all_votes	yes_votes	no_votes	abstain	idealpoint_estimate	affinityscore_usa	affinityscore_russia	affinityscore_china	affinityscore_india	affinityscore_brazil	affinityscore_israel	cluster
9685	1996.0	51.0	990	Samoa	74.0	64.0	0.0	10.0	0.2483	0.3378	0.6575	0.6892	0.6216	0.8630	0.2917	2
9686	1997.0	52.0	990	Samoa	66.0	56.0	1.0	9.0	0.2542	0.3485	0.6818	0.6818	0.6212	0.8636	0.2769	2
9687	1998.0	53.0	990	Samoa	57.0	49.0	0.0	8.0	0.1540	0.2456	0.6667	0.6429	0.6140	0.8772	0.2281	2
9688	1999.0	54.0	990	Samoa	62.0	50.0	1.0	11.0	0.2465	0.2742	0.7258	0.5968	0.6129	0.8548	0.2787	2
9689	2000.0	55.0	990	Samoa	62.0	52.0	2.0	8.0	0.2734	0.2742	0.6774	0.6613	0.6129	0.8710	0.2419	2
9690	2001.0	56.0	990	Samoa	37.0	30.0	3.0	4.0	0.2417	0.3784	0.5405	0.5405	0.5135	0.7568	0.3784	0
9691	2002.0	57.0	990	Samoa	62.0	52.0	2.0	8.0	0.1959	0.1613	0.6167	0.6885	0.6290	0.8387	0.1967	2
9692	2003.0	58.0	990	Samoa	67.0	55.0	1.0	11.0	0.1806	0.1493	0.7164	0.6818	0.6269	0.7612	0.1818	2
9693	2004.0	59.0	990	Samoa	65.0	51.0	2.0	12.0	0.2033	0.1692	0.6563	0.6406	0.5692	0.6308	0.1563	2
9694	2005.0	60.0	990	Samoa	71.0	58.0	2.0	11.0	0.1984	0.1714	0.6429	0.7143	0.6479	0.7746	0.2239	2
9695	2006.0	61.0	990	Samoa	80.0	59.0	3.0	18.0	0.2754	0.1875	0.6500	0.6835	0.6076	0.7750	0.2911	2
9696	2007.0	62.0	990	Samoa	66.0	55.0	1.0	10.0	0.1086	0.0909	0.6769	0.7846	0.6970	0.8333	0.2121	2
9697	2008.0	63.0	990	Samoa	69.0	58.0	2.0	9.0	0.1493	0.1449	0.6232	0.6866	0.6377	0.7971	0.2464	2
9698	2009.0	64.0	990	Samoa	64.0	50.0	2.0	12.0	0.1717	0.1719	0.6563	0.7344	0.6406	0.7500	0.1587	2
9699	2010.0	65.0	990	Samoa	65.0	53.0	2.0	10.0	0.2148	0.2000	0.6462	0.7188	0.6462	0.8000	0.2031	2
9700	2011.0	66.0	990	Samoa	59.0	48.0	1.0	10.0	0.2350	0.2881	0.6102	0.6780	0.6271	0.7458	0.2105	2
9701	2012.0	67.0	990	Samoa	68.0	56.0	0.0	12.0	0.2359	0.1912	0.6324	0.6515	0.6618	0.7941	0.1765	2
9702	2013.0	68.0	990	Samoa	62.0	51.0	0.0	11.0	0.1735	0.1935	0.5806	0.7097	0.6452	0.7742	0.1500	2
9703	2014.0	69.0	990	Samoa	75.0	65.0	0.0	10.0	0.1007	0.2344	0.5714	0.6984	0.6615	0.8154	0.2000	2
9704	2015.0	70.0	990	Samoa	67.0	59.0	0.0	8.0	-0.0227	0.2090	0.5672	0.6866	0.6567	0.8507	0.1642	2

	year	assembly_session	state_code	all_votes	yes_votes	no_votes	abstain	idealpoint_estimate	affinityscore_usa	affinityscore_russia	affinityscore_china	affinityscore_india	affinityscore_brazil	affinityscore_israel
count	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000	9697.000000
mean	1987.037125	42.037125	446.914613	75.246674	59.793235	5.647932	9.805507	-0.000279	0.293589	0.620304	0.752558	0.687353	0.733821	0.350540
std	18.478671	18.478671	258.472010	33.043167	32.657278	8.268681	9.713783	0.989763	0.203660	0.202982	0.160692	0.195748	0.186575	0.189557
min	1946.000000	1.000000	2.000000	1.000000	0.000000	0.000000	0.000000	-2.562400	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	1973.000000	28.000000	220.000000	58.000000	38.000000	0.000000	4.000000	-0.661100	0.140800	0.512200	0.723100	0.526300	0.615400	0.193500
50%	1989.000000	44.000000	437.000000	68.000000	57.000000	2.000000	7.000000	-0.175500	0.235300	0.652200	0.761200	0.754100	0.800000	0.325900
75%	2003.000000	58.000000	660.000000	86.000000	71.000000	9.000000	13.000000	0.808900	0.388100	0.737700	0.869600	0.835800	0.880000	0.466700
max	2015.000000	70.000000	990.000000	158.000000	156.000000	98.000000	73.000000	3.004200	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000

ML CAC¶

* Name: Shruti Mall¶

* Register Number: 23122032¶

* Class:MSc DS A¶

* Date :16/05/24¶

Dataset Descrtiption¶

Tools and Libraries¶

Random Forest Classifier¶

K Means¶

Linear Regression¶

ARIMA(AutoRegressive Integrated Moving Average)¶